INDEX

Explanations

technical terms related to programming and data structures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tonode

-0.63

ModelAttribute

-0.53

seamnă

-0.50

==>

-0.48

**

-0.46

 CreateTagHelper

-0.45

rschein

-0.45

unkel

-0.45

adaan

-0.45

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.94

Tikang

0.92

abestanden

0.87

 EconPapers

0.80

 autorytatywna

0.78

enumi

0.76

MemoryWarning

0.75

 للاسماء

0.73

Clik

0.72

WebVitals

0.70

Activations Density 0.284%

technical terms related to programming and data structures

No Comments

No Known Activations